| Abstrakt: |
Road extraction from satellite data is of great importance in various fields such as climate change, urban planning, forestry and sustainable development. In addition, fast and accurate road detection plays a critical role in disaster management and smart city applications, especially in emergency situations. In this context, U-net architecture provides an effective solution for tasks such as semantic segmentation and urban planning support. In this work, Edge U-net, a different adaptation of the U-net architecture, is used to map roads and streets and to detect changes over time. When the performance of the architecture is evaluated using Mean Intersection over Union (mIoU) and global accuracy metrics, superior results are obtained compared to other studies in the literature. In addition, the performance of the model was improved by applying transfer learning to the ImageNet dataset and various hyperparameter settings were performed. The results of the study show that path inferences are detected with 98.4% accuracy. These results show that Edge U-Net architecture and deep learning methods can be effectively used in road detection applications from satellite imagery. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink